team-polish

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection where malicious instructions embedded in the feature or area being analyzed could hijack the sub-agents' behavior. Since the sub-agents have access to powerful tools like Bash and file editing, this poses a risk of unauthorized command execution or data modification.\n
  • Ingestion points: The [feature or area to polish] argument is used as a direct input to define the context for the performance-analyst, technical-artist, sound-designer, and qa-tester sub-agents.\n
  • Boundary markers: The instructions do not define any delimiters (e.g., XML tags or triple quotes) or specific 'ignore embedded instructions' warnings when passing external content to the sub-agents.\n
  • Capability inventory: The skill and its sub-agents are granted access to a wide range of sensitive tools, including Bash (for profiling and optimization), Task (for recursive sub-agent spawning), Write, Edit, and TodoWrite.\n
  • Sanitization: There is no evidence of input validation, escaping, or filtering of the user-provided feature path or content before it is processed by the agent pipeline.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 11:07 PM